T-Head C908 (cycles):
rv34_idct_dc_add_c: 113.2
rv34_idct_dc_add_rvv_i32: 48.5 (before)
rv34_idct_dc_add_rvv_i32: 39.5 (after)
---
libavcodec/riscv/rv34dsp_rvv.S | 19 +++++++++++--------
1 file changed, 11 insertions(+), 8 deletions(-)
diff --git a/libavcodec/riscv/rv34dsp_rvv.S b/libavcodec/riscv/rv34dsp_rvv.S
index 98871507c2..70c88fdca5 100644
--- a/libavcodec/riscv/rv34dsp_rvv.S
+++ b/libavcodec/riscv/rv34dsp_rvv.S
@@ -42,14 +42,17 @@ func ff_rv34_idct_dc_add_rvv, zve32x
mul t1, t1, a2
addi t1, t1, 512
srai t1, t1, 10
- vsetivli zero, 4*4, e16, m2, ta, ma
- vzext.vf2 v2, v0
- vadd.vx v2, v2, t1
- vmax.vx v2, v2, zero
- vsetvli zero, zero, e8, m1, ta, ma
- vnclipu.wi v0, v2, 0
- vsetivli zero, 4, e8, mf4, ta, ma
- vsse32.v v0, (a0), a1
+ vsetivli zero, 4*4, e8, m2, ta, ma
+ bgez t1, 1f
+ neg t1, t1
+ vssubu.vx v0, v0, t1
+ vsetivli zero, 4, e8, mf4, ta, ma
+ vsse32.v v0, (a0), a1
+ ret
+1:
+ vsaddu.vx v0, v0, t1
+ vsetivli zero, 4, e8, mf4, ta, ma
+ vsse32.v v0, (a0), a1
ret
endfunc
--
2.45.2
_______________________________________________
ffmpeg-devel mailing list
[email protected]
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
[email protected] with subject "unsubscribe".